Description

The widespread adoption of computer vision models is often constrained by the issue of domain mismatch. Models that are trained with data belonging to one distribution, perform poorly when tested with data from a different distribution.

Reuse Permissions
  • Downloads
    pdf (2.9 MB)

    Download count: 0

    Details

    Contributors
    Date Created
    2017
    Resource Type
  • Text
  • Collections this item is in
    Note
    • Doctoral Dissertation Computer Science 2017

    Machine-readable links